Gemini 3.5 Flash Lite via the Tokenator API
What the model is for
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
Specification
| Full name | Gemini 3.5 Flash Lite |
| API ID | gemini-3.5-flash-lite |
| Model vendor | Gemini |
| Type | Text model (chat / completions) |
| Context window | 1.05M tokens |
| Max output | 65.5K tokens |
| Image input | yes |
| Tokenator usage multiplier | 0.4× |
| Output token multiplier | 1× |
| Input modalities | text, image, audio, video, file |
| Aliases | cursor-gemini-3.5-flash-lite |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-22 |
Benchmarks
| Intelligence index | 11.7 |
| Vals Index (Vals AI) | 36.7% |
| Code Migration (Vals AI) | 6.1% |
| IOI v1 (Vals AI) | 26.2% |
| LiveCodeBench (Vals AI) | 79% |
| ProgramBench (Vals AI) | 0% |
| SWE-bench (Vals AI) | 75% |
| Terminal-Bench 2.1 (Vals AI) | 50.2% |
| Vibe Code Bench v1.1 (Vals AI) | 37.2% |
| GPQA Diamond (Vals AI) | 83.8% |
| MMLU Pro (Vals AI) | 85.8% |
| MMMU Pro (Vals AI) | 83.6% |
| ProofBench v1 (Vals AI) | 13% |
| CorpFin v2 (Vals AI) | 60.7% |
| EMB (Vals AI) | 43.2% |
| Finance Agent (v2) (Vals AI) | 47.4% |
| MortgageTax (Vals AI) | 68.7% |
| Tax Agent Bench (Vals AI) | 7.3% |
| TaxEval v2 (Vals AI) | 72.6% |
| Harvey's Legal Agent Benchmark v1 (Vals AI) | 0% |
| Immigration (Vals AI) | 55.7% |
| Legal Research Bench (Vals AI) | 13.9% |
| LegalBench (Vals AI) | 84.1% |
| MedCode (Vals AI) | 43.5% |
| MedScribe (Vals AI) | 70.9% |
| CyberBench v1.1 (Vals AI) | 59.1% |
| SAGE (Vals AI) | 79.5% |
| Financial Coaching Bench (Vals AI) | 57.5% |
| Public Benefits Bench v1.1 (Vals AI) | 51.8% |
Artificial Analysis and Vals AI data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier | Output token multiplier |
|---|---|---|
| Gemini Partner #1 | 0.4× | 1× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/chat/completions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gemini-3.5-flash-lite", "messages": [{"role": "user", "content": "Hello"}] }'
Compatible tools
The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.
See also
FAQ about Gemini 3.5 Flash Lite
What is the API ID of Gemini 3.5 Flash Lite?
gemini-3.5-flash-lite — put this into the model field of your request.
What context window does Gemini 3.5 Flash Lite have?
1.05M tokens; max output is 65.5K tokens.
How many tokens will a request cost?
(input × 0.4×) + (output × 1×). See the documentation for details.
Which tools support this model?
Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.